© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40014
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Henderson
    -0.27
     Humph
    -0.26
    EAR
    -0.25
    ,\↵
    -0.25
    rowning
    -0.24
     Mata
    -0.24
    ONO
    -0.24
    ayı
    -0.23
    aters
    -0.23
    èŀ³
    -0.23
    POSITIVE LOGITS
    åĪ®
    0.26
    åħ·ä½ĵåĨħ容
    0.26
    è¿Ŀè§Ħ
    0.26
    åľ¨å½ĵåľ°
    0.26
     replies
    0.26
    åĪĴ
    0.26
     endanger
    0.26
    ä¸įæķ¢
    0.25
    ä¸įèµ·
    0.25
    geo
    0.25
    Activations Density 2.851%

    No Known Activations

    This feature has no known activations.